diff --git a/skills/ms-ai-engineering/references/api-management/security-hardening-ai-gateway.md b/skills/ms-ai-engineering/references/api-management/security-hardening-ai-gateway.md
index da8ba2b..117d408 100644
--- a/skills/ms-ai-engineering/references/api-management/security-hardening-ai-gateway.md
+++ b/skills/ms-ai-engineering/references/api-management/security-hardening-ai-gateway.md
@@ -1,6 +1,6 @@
 # Security Hardening for AI Gateways in APIM
 
-**Last updated:** 2026-02
+**Last updated:** 2026-06-24
 **Status:** GA
 **Category:** API Management & AI Gateway
 
@@ -103,17 +103,17 @@ Prompt injection er den mest kritiske AI-spesifikke trusselen (OWASP LLM Top 10
     <inbound>
         <base />
         <!-- Azure AI Content Safety for prompt moderation -->
-        <llm-content-safety backend-id="content-safety-backend">
-            <text-blocklist-ids>
-                <id>prompt-injection-patterns</id>
-                <id>offensive-content-no</id>
-            </text-blocklist-ids>
+        <llm-content-safety backend-id="content-safety-backend" shield-prompt="true">
             <categories>
                 <category name="Hate" threshold="2" />
                 <category name="Violence" threshold="2" />
                 <category name="SelfHarm" threshold="2" />
                 <category name="Sexual" threshold="2" />
             </categories>
+            <blocklists>
+                <id>prompt-injection-patterns</id>
+                <id>offensive-content-no</id>
+            </blocklists>
         </llm-content-safety>
     </inbound>
 </policies>